© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15422
    Prev
    Next
    INDEX
    Explanations

    followed by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĽ´
    -0.08
    mere
    -0.08
    kad
    -0.08
     bald
    -0.08
     butcher
    -0.08
     smarter
    -0.07
     Spin
    -0.07
     happier
    -0.07
    ['__
    -0.07
     (!((
    -0.07
    POSITIVE LOGITS
     second
    0.36
     secondary
    0.32
     followed
    0.32
    second
    0.32
     SECOND
    0.29
     next
    0.27
     Secondary
    0.27
    Second
    0.27
    -second
    0.27
    Secondary
    0.27
    Activations Density 0.432%

    No Known Activations